[Fix]Fixed the issue where type and by_epoch in loop_cfg exist simult… #11085
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…aneously during training in solo_r50_fpn_3x_coco configuration, resulting in failure to train.
|
|
hhaAndroid
approved these changes
Oct 26, 2023
yumion
pushed a commit
to yumion/mmdetection
that referenced
this pull request
Jan 31, 2024
yumion
pushed a commit
to yumion/mmdetection
that referenced
this pull request
Jan 31, 2024
ChuaHanChong
added a commit
to Porolis-Technologies/AI_mmdetection
that referenced
this pull request
Nov 15, 2024
* Fix docstring for dimension of targets argument (open-mmlab#11058) * Fix Grounding DINO nan when class tokens exceeds 256 (open-mmlab#11066) * Fix broken links in README.md (open-mmlab#11060) * Fixed the issue where the directory level of the youtubevis2coco… (open-mmlab#11086) * Fixed the issue where type and by_epoch in loop_cfg exist simult… (open-mmlab#11085) * Support ODinW and evaluate (open-mmlab#11105) * [MMSIG#357] Add new configs for panoptic_fpn (open-mmlab#11109) * [Feature] Add optional score threshold option to coco_error_analysis.py (open-mmlab#11117) * Support LVIS chunked evaluation and image chunked inference of GLIP (open-mmlab#11136) * Replace partially weighted download links with OpenXLab for the Faster-RCNN (open-mmlab#11173) * add odinw configs and evaluation results of GLIP(open-mmlab#11175) * Add GroundingDINO on ODinW results, and support caption prompt of GroundingDINO (open-mmlab#11187) * MMGroundingDINO-A replicable and more comprehensive GroundingDINO (open-mmlab#11295) Co-authored-by: Cycyes <92714336 [email protected]> * finetune MM-GDINO on ov_coco and ov_lvis (open-mmlab#11304) * [Feature] Add RTMDet Swin / ConvNeXt (open-mmlab#11259) * Fix bug in `convert_coco_format` (open-mmlab#11251) * Fix CO-DETR load_from url in config (open-mmlab#11220) * Update README and refine of MM-GDINO (open-mmlab#11298) * Fixed mask shape after Albu postprocess (open-mmlab#11280) * update English version of md (open-mmlab#11336) * Fix one of the CO-DETR config files (open-mmlab#11325) * replace '.jpg' instead of 'jpg' to guarantee replacing file ending (open-mmlab#11340) * Bump version to 3.3.0 (open-mmlab#11338) * [Bug Fix] video_demo bug fixed for issue#11353 (open-mmlab#11451) * use `lerp` in ema (open-mmlab#11442) * fix:grounding_pretrain_text_trans_negative_label (open-mmlab#11404) * Release MM-GroundingDINO SwinB and SwinL Weights (open-mmlab#11458) --------- Co-authored-by: Mathias Réus <93187038 [email protected]> Co-authored-by: Jinhyung Park <[email protected]> Co-authored-by: Aaron Sun <[email protected]> Co-authored-by: LRJKD <101466907 [email protected]> Co-authored-by: Haian Huang(深度眸) <[email protected]> Co-authored-by: Lei Lei <18294546 [email protected]> Co-authored-by: Leaf Ying <43506966 [email protected]> Co-authored-by: key <30455795 [email protected]> Co-authored-by: Cycyes <92714336 [email protected]> Co-authored-by: Shilin Xu <[email protected]> Co-authored-by: takuoko <[email protected]> Co-authored-by: Jaewoo Choi <130287161 [email protected]> Co-authored-by: Lintch <44701395 [email protected]> Co-authored-by: ilcopione <109541948 [email protected]> Co-authored-by: Adnan Mujagic <[email protected]> Co-authored-by: R-Fehler <36566250 [email protected]> Co-authored-by: Jun0922 <89365607 [email protected]> Co-authored-by: RangiLyu <[email protected]> Co-authored-by: Chen Qibo <69334887 [email protected]>
ChuaHanChong
added a commit
to Porolis-Technologies/AI_mmdetection
that referenced
this pull request
Nov 15, 2024
* Fix docstring for dimension of targets argument (open-mmlab#11058) * Fix Grounding DINO nan when class tokens exceeds 256 (open-mmlab#11066) * Fix broken links in README.md (open-mmlab#11060) * Fixed the issue where the directory level of the youtubevis2coco… (open-mmlab#11086) * Fixed the issue where type and by_epoch in loop_cfg exist simult… (open-mmlab#11085) * Support ODinW and evaluate (open-mmlab#11105) * [MMSIG#357] Add new configs for panoptic_fpn (open-mmlab#11109) * [Feature] Add optional score threshold option to coco_error_analysis.py (open-mmlab#11117) * Support LVIS chunked evaluation and image chunked inference of GLIP (open-mmlab#11136) * Replace partially weighted download links with OpenXLab for the Faster-RCNN (open-mmlab#11173) * add odinw configs and evaluation results of GLIP(open-mmlab#11175) * Add GroundingDINO on ODinW results, and support caption prompt of GroundingDINO (open-mmlab#11187) * MMGroundingDINO-A replicable and more comprehensive GroundingDINO (open-mmlab#11295) Co-authored-by: Cycyes <92714336 [email protected]> * finetune MM-GDINO on ov_coco and ov_lvis (open-mmlab#11304) * [Feature] Add RTMDet Swin / ConvNeXt (open-mmlab#11259) * Fix bug in `convert_coco_format` (open-mmlab#11251) * Fix CO-DETR load_from url in config (open-mmlab#11220) * Update README and refine of MM-GDINO (open-mmlab#11298) * Fixed mask shape after Albu postprocess (open-mmlab#11280) * update English version of md (open-mmlab#11336) * Fix one of the CO-DETR config files (open-mmlab#11325) * replace '.jpg' instead of 'jpg' to guarantee replacing file ending (open-mmlab#11340) * Bump version to 3.3.0 (open-mmlab#11338) * [Bug Fix] video_demo bug fixed for issue#11353 (open-mmlab#11451) * use `lerp` in ema (open-mmlab#11442) * fix:grounding_pretrain_text_trans_negative_label (open-mmlab#11404) * Release MM-GroundingDINO SwinB and SwinL Weights (open-mmlab#11458) --------- Co-authored-by: Mathias Réus <93187038 [email protected]> Co-authored-by: Jinhyung Park <[email protected]> Co-authored-by: Aaron Sun <[email protected]> Co-authored-by: LRJKD <101466907 [email protected]> Co-authored-by: Haian Huang(深度眸) <[email protected]> Co-authored-by: Lei Lei <18294546 [email protected]> Co-authored-by: Leaf Ying <43506966 [email protected]> Co-authored-by: key <30455795 [email protected]> Co-authored-by: Cycyes <92714336 [email protected]> Co-authored-by: Shilin Xu <[email protected]> Co-authored-by: takuoko <[email protected]> Co-authored-by: Jaewoo Choi <130287161 [email protected]> Co-authored-by: Lintch <44701395 [email protected]> Co-authored-by: ilcopione <109541948 [email protected]> Co-authored-by: Adnan Mujagic <[email protected]> Co-authored-by: R-Fehler <36566250 [email protected]> Co-authored-by: Jun0922 <89365607 [email protected]> Co-authored-by: RangiLyu <[email protected]> Co-authored-by: Chen Qibo <69334887 [email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
…aneously during training in solo_r50_fpn_3x_coco configuration, resulting in failure to train.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Fixed the issue where type and by_epoch in loop_cfg exist simultaneously during training in solo_r50_fpn_3x_coco configuration, resulting in failure to train.
Modification
Modified solo_r50_fpn_3x_coco configuration file.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist